© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 3935
    Prev
    Next
    INDEX
    Explanations

    biggest football

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tı
    2.67
    tin
    2.41
    t
    2.39
    tır
    2.25
    eo
    2.25
    h
    2.21
    er
    2.18
    י
    2.18
    tac
    2.17
    oys
    2.11
    POSITIVE LOGITS
    циями
    1.36
    ция
    1.34
    轭
    1.32
    цией
    1.31
    ций
    1.31
     chewed
    1.28
    appendChild
    1.26
     academics
    1.24
    Bedroom
    1.23
    ensed
    1.23
    Activations Density 0.079%

    No Known Activations